Deep Q-learning in traffic control of BelAZ mining dump trucks at the deposits of the Kursk Magnetic Anomaly

Yu.N. Shedko, K.V. Kharchenko, S.A. Zudenkova, A.I. Galkin, L.K. Babayan
Financial University under the Government of the Russian Federation, Moscow, Russian Federation
Russian Mining Industry №1/ 2026 p. 105-113

Abstract: Iron ore open-pit mines of the Kursk Magnetic Anomaly (KMA) are characterized with extreme operating conditions of the transport systems characterized with the mining depth up to 600 m, the annual volume of rock mass transportation of over 50 million tons, and the fleet of up to 38 BelAZ dump trucks of various payloads. Traditional traffic control systems demonstrate limited adaptability to dynamic changes in the production environment, which creates a need to develop smart control algorithms. The study is aimed at implementing the Double Deep Q-Network algorithm to optimize vehicle routing at the Lebedinsky Mining and Processing Plant. A discrete-event model of the mining transport complex was integrated with a neural network architecture that enables formation of adaptive control policies through interaction with the simulated environment. Experimental data of international studies on application of Deep Q-Learning in open-pit mines demonstrate a 5.56–5.7% increase in transport system performance compared to fixed traffic control strategies. Queue duration is reduced by an average of 24.4%, with maximum values of up to 45.2% in stress scenarios involving equipment failures. Energy efficiency increases due to minimized unproductive downtime, which leads to a reduction in direct greenhouse gas emissions by 10–30%, depending on the fleet configuration and intensity of operations. The reinforcement learning algorithm can be scaled up to mixed fleets that include BelAZ-75131 dump trucks with the payload of 130 tons, BelAZ-75710 dump trucks with the payload of 450 tons, and Chinese ESTAR ESDE240 dump trucks with the payload of 240 tons, which are introduced at KMA enterprises starting from 2024. Practical implementation requires integration with the existing GTK Karier Automated Control Systems and adaptation to the specific features of iron ore deposits with the iron content of 38-52% in various types of ore.

Keywords: Deep Q-learning, traffic control of the mine transport, Kursk Magnetic Anomaly, BelAZ, reinforcement learning, mining transport complex, production optimization

For citation: Shedko Yu.N., Kharchenko K.V., Zudenkova S.A., Galkin A.I., Babayan L.K. Deep Q-learning in traffic control of BelAZ mining dump trucks at the deposits of the Kursk Magnetic Anomaly. Russian Mining Industry. 2026;(1):105–113. https://doi.org/10.30686/1609-9192-2026-1-105-113

Информация о статье

Поступила в редакцию: 19.10.2025

Поступила после рецензирования: 16.12.2025

Принята к публикации: 20.01.2026

Информация об авторах

Yuri N. Shedko — Dr. Sci. (Econ.), Professor of the Department of State and Municipal Administration of the Financial University under the Government of the Russian Federation, Moscow, Russian Federation; https://orcid.org/0000-0002-9179-3637; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Konstantin V. Kharchenko — Cand. Sci. (Sociol.), Associate Professor of the Department of State and Municipal Administration of the Financial University under the Government of the Russian Federation, Moscow, Russian Federation; https://orcid.org/0000-0003-3329-7755; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Svetlana A. Zudenkova — Cand. Sci. (Econ.), Associate Professor of the Department of State and Municipal Administration of the Financial University under the Government of the Russian Federation, Moscow, Russian Federation; https://orcid.org/0000-0002-6470-5451; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Andrey I. Galkin — Cand. Sci. (Econ.), Associate Professor of the Department of State and Municipal Administration of the Financial University under the Government of the Russian Federation, Moscow, Russian Federation; https://orcid.org/0000-0003-0021-7536; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Levon K. Babayan — Cand. Sci. (Econ.), Assistant of the Department of State and Municipal Administration of the Financial University under the Government of the Russian Federation, Moscow, Russian Federation; https://orcid.org/0000-0001-6872-8549; e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Список литературы

1. Plaksenko N.A. Glavneishie zakonomernosti zhelezorudnogo osadkonakopleniya v dokembrii (na primere Kurskoi magnitnoi anomalii). Voronezh: Izd-vo Voronezhskogo un-ta; 1966. 264 s. (In Russ.) Available at: https://www.geokniga.org/node/19212 (accessed: 27.10.2025).

2. Kalganov M.I., Kossovskii M.A. Velikii dar prirody. M.: Nedra; 1968. 255 s. (In Russ.)

3. Ta C.H., Kresta J.V., Forbes J.F., Marquez H.J. A stochastic optimization approach to mine truck allocation. International Journal of Surface Mining, Reclamation and Environment. 2005;19(3):162–175. https://doi.org/10.1080/13895260500128914

4. Alarie S., Gamache M. Overview of solution strategies used in truck dispatching systems for open pit mines. International Journal of Surface Mining, Reclamation and Environment. 2002;16(1):59–76. https://doi.org/10.1076/ijsm.16.1.59.3408

5. Zhang L., Xia X. An integer programming approach for truck-shovel dispatching problem in open-pit mines. Energy Procedia. 2015;75:1779–1784. https://doi.org/10.1016/j.egypro.2015.07.469

6. Ahangaran D.K., Yasrebi A.B., Wetherelt A., Foster P. Real-time dispatching modelling for trucks with different capacities in open pit mines. Archives of Mining Sciences. 2012;57(1):39–52. https://doi.org/10.2478/v10267-012-0003-8

7. Sutton R.S., Barto A.G. Reinforcement learning: An introduction. 2nd ed. Cambridge, MA: MIT Press, 2018. 552 p.

8. Mnih V., Kavukcuoglu K., Silver D., Rusu A.A., Veness J., Bellemare M.G. et al. Human-level control through deep reinforcement learning. Nature. 2015;518(7540):529–533. https://doi.org/10.1038/nature14236

9. Zhang C., Odonkor P., Zheng S., Khorasgani H., Serita S., Gupta C. Dynamic dispatching for large-scale heterogeneous fleet via multi-agent deep reinforcement learning. In: 2020 IEEE International Conference on Big Data (Big Data), Atlanta, 10–13 December 2020. IEEE; 2020, pp. 1436–1441. https://doi.org/10.1109/BigData50022.2020.9378191

10. Huo D., Sari Y.A., Kealey R., Zhang Q. Reinforcement learning-based fleet dispatching for greenhouse gas emission reduction in open-pit mining operations. Resources, Conservation and Recycling. 2023;188:106664. https://doi.org/10.1016/j.resconrec.2022.106664

11. Koryagin M., Voronov A. Improving the organization of the shovel-truck systems in open-pit coal mines. Transport Problems. 2017;12(2):113–122. https://doi.org/10.20858/tp.2017.12.2.11

12. Kadyrova G.M., Krasyukova N.L., Rozhdestvenskaya I.A., Tokmurzin T.M., Voronova E.I. Adaptive optimization of traffic flows in underground mine workings based on artificial intelligence methods. Russian Mining Industry. 2025;(1):137–146. (In Russ.) https://doi.org/10.30686/1609-9192-2025-1-137-146

13. Panina O.V., Popadyuk N.K., Eremin S.G., Tokmurzin T.M., Razumova E.V. Application of the BigData technologies to optimize production processes in the Russian mining industry: analysis of implementation and efficiency. Russian Mining Industry. 2024;(6):178–185. (In Russ.) https://doi.org/10.30686/1609-9192-2024-6-178-185

14. Banerjee C., Nguyen K., Fookes C. Mining-Gym: A configurable RL benchmarking environment for truck dispatch scheduling. arXiv:2503.19195v1. 24 March 2025. 40 p. Available at: https://arxiv.org/pdf/2503.19195 (accessed: 27.10.2025).

15. Panina O.V., Belyaev A.M., Zavalko N.A., Eremin S.G., Sagina O.A. Application of deep machine learning methods for structural analysis of ore bodies and prediction of optimal mining zones. Russian Mining Industry. 2025;(1):177–183. (In Russ.) https://doi.org/10.30686/1609-9192-2025-1-177-183

16. Borisova O.V., Dreving S.R., Loseva O.V., Fedotova M.A. State financial support measures and risk factors affecting the cost of investment projects for the introduction of industrial robotic complex. Finance: Theory and Practice. 2025;29(3):20–34. (In Russ.) https://doi.org/10.26794/2587-5671-2025-29-3-20-34

17. Panina O.V., Popadyuk N.K., Eremin S.G., Tokmurzin T.M., Razumova E.V. Application of the BigData technologies to optimize production processes in the Russian mining industry: analysis of implementation and efficiency. Russian Mining Industry. 2024;(6):178–185. (In Russ.) https://doi.org/10.30686/1609-9192-2024-6-178-185

18. Kosorukov O.A., Mishchenko A.V., Sviridova O.A., Tsurkov V.I. Dynamic models of transport resources management. Izvestiya Rossiiskoi Akademii Nauk. Teoriya i Sistemy Upravleniya. 2025;(6):108–129. (In Russ.)

19. Yeganejou M., Badiozamani M., Moradi-Afrapoli A., Askari-Nasab H. Integration of simulation and dispatch modelling to predict fleet productivity: an open-pit mining case. Mining Technology: Transactions of the Institutions of Mining and Metallurgy. 2022;131(2):67–79. https://doi.org/10.1080/25726668.2021.2001255

20. Karaev A.K., Borisova O.V. Prospective models of financial forecasting of budget revenues. Finance: Theory and Practice. 2025;29(1):20–33. (In Russ.) https://doi.org/10.26794/2587-5671-2025-29-1-20-33

21. Moradi Afrapoli A., Askari-Nasab H. Mining fleet management systems: a review of models and algorithms. International Journal of Mining, Reclamation and Environment. 2019;33(1):42–60. https://doi.org/10.1080/17480930.2017.1336607

22. Rozhdestvenskaya I.A., Belyaev A.M., Lukichev K.E., Zubenko A.V., Laffakh A.M. Development of smart distributed data storage and analysis systems for optimization of mining operations and coal mining management. Russian Mining Industry. 2025;(2):56–64. (In Russ.) https://doi.org/10.30686/1609-9192-2025-2-56-64